For consultancies, agencies and professional firms
Your firm's judgment. On tap.
distill.pm distills your email, chat and documents, and turns the lessons your firm has actually lived into a playbook your whole team can consult.
Nobody writes anything.
The partner who resigns on Friday takes nineteen years of judgment with her.
The bid you price tomorrow repeats a mistake from the one you lost last year.
A new hire spends their first year learning how the firm works by asking around.
Somebody built a wiki once. Nobody maintains it and nobody trusts it.
The answers already exist. They are sitting in years of email, chat and documents.
Never quote a large fixed price from a brief alone. Sell a short paid discovery first.
Lesson 112 · Pricing and quoting · Recorded 9 times
Meridian Health · March 2024
“Send us one number for the whole portal and we can get it approved.”
We proposed a one day paid discovery at a reduced rate, then quoted the build in three phases. The quote held to the day and the client renewed the following year.
Gmail · thread: Portal pricing · 14 Mar 2024
Fenwick & Long · September 2022
“We have decided to go with a supplier who could quote straight from the brief.”
We had given a fixed total against two pages. The scope grew through the build, we absorbed the overrun, and they left anyway.
Gmail · thread: Proposal follow-up · 9 Sep 2022
Every lesson looks like this: the rule, the real occasions it came from, and the documents one click away.
One question, answered from the playbook
“Pricing the Meridian Health patient portal bid tomorrow. They want one fixed number against their brief. What do we know?”
Sell the discovery day first. Do not give one fixed number tomorrow.
Three rules apply, in this order. The first one cost the firm four days on Halston Logistics last month.
Never price integration work fixed until we have seen the other system's API documents. 1 time
Never quote a large fixed price from a brief alone. Sell a short paid discovery first. 9 times
Price the phase you understand, not the year you do not. 12 times
The benchmark
Four in ten. The rest is yours alone.
A general AI model already makes your firm's call about four times in ten. The other six live only in your archive. We measure the split on your own material, so you know exactly what you're sitting on.
Asked situations from your firm's own history, a general AI model makes a call your experience says is worse about half the time. That gap is what your archive is worth.
What you get
01
The Playbook.
Every lesson your firm has learned: the rule, the real occasions it was learned from, each with what happened, how it ended, and the original documents a click away.
02
Ask.
Put a situation to it, get your firm's answer, with the lessons it used cited beside the reply. Working a bid, it also lines up the material worth reusing: the closest past proposals, the case-study slides, the answers you wrote last time, each a click from its source.
03
Plays.
For the situations that keep coming back: pricing a bid, kicking off, a client threatening to walk. A play holds the lessons in the order they apply. Read it on the way in.
04
The record grows itself.
On a schedule, distill.pm reads what's new, adds lessons, and enriches old ones with new examples, including the ones that went wrong. It also reads its own record for trends: when the firm quietly stops following one of its own rules, it notices, and asks you whether that was deliberate. You review only what it is unsure about.
How it works
01
Connect
Google Workspace, Microsoft 365, Slack, or upload an archive.
02
We distill
The situations where judgment was exercised become lessons, with the source documents a click away.
03
You review
Confirm new lessons, reword the ones that have changed. Minutes, not days.
04
Your team uses it
Playbook, chat, API.
We read, we distill, we discard. distill.pm keeps lessons and pointers, not your archive. Your documents stay in your systems.
The identity layer
It knows who's who. Nobody else has to.
A decade of mail mentions five different Pauls, three nicknames and a client who changed companies twice. distill.pm builds the who's-who of your firm's history, so every lesson stays traceable to the people and clients it came from. Names are replaced with neutral labels the moment documents are read, kept apart from the lessons, and shown only to the readers you permit. In a private build, they never leave your systems at all.
The API
Readable by your systems. Usable by your agents.
The whole playbook is available over a read-only API and as an MCP server your own AI agents can plug into. An AI assistant drafting a proposal pulls the applicable lessons and the reusable material the same way a person would, and cites them the same way too.
Built on ourselves first: twelve years of a real consultancy's email, chat and documents.
12
Years of our own archive
1,000,000+
Documents read
1,400+
Lessons, with receipts
See what your own material holds.
Prefer mail? info@distill.pm
distill.pm · a Fluxus product · info@distill.pm